The size of Rx completion queue should be doubled if compression is enabled
in case of non-vectorized Rx.
Fixes: 523f5a742102 ("net/mlx5: fix configuration of Rx CQE compression")
Cc: [email protected]
Signed-off-by: Yongseok Koh <[email protected]>
Acked-by: Nelio Laranjeiro <[email protected]>
---
drivers/net/mlx5/mlx5_rxq.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/mlx5/mlx5_rxq.c b/drivers/net/mlx5/mlx5_rxq.c
index 632d45103..ad741ef44 100644
--- a/drivers/net/mlx5/mlx5_rxq.c
+++ b/drivers/net/mlx5/mlx5_rxq.c
@@ -617,7 +617,7 @@ mlx5_priv_rxq_ibv_new(struct priv *priv, uint16_t idx)
* make cq_ci and rq_ci aligned.
*/
if (rxq_check_vec_support(rxq_data) < 0)
- cqe_n *= 2;
+ attr.cq.ibv.cqe *= 2;
} else if (priv->cqe_comp && rxq_data->hw_timestamp) {
DEBUG("Rx CQE compression is disabled for HW timestamp");
}
--
2.13.5 (Apple Git-94)
